Neuro-Symbolic Synergy for Interactive World Modeling
This addresses the need for reliable world models in interactive environments like ScienceWorld, Webshop, and Plancraft, representing an incremental improvement over existing methods.
The paper tackled the problem of large language models hallucinating as world models by proposing Neuro-Symbolic Synergy (NeSyS), which integrates LLMs with symbolic rules to improve expressivity and robustness, achieving a 50% reduction in training data without accuracy loss.
Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs), where strict compliance with deterministic transition rules--particularly in corner cases--is essential. In contrast, Symbolic WMs provide logical consistency but lack semantic expressivity. To bridge this gap, we propose Neuro-Symbolic Synergy (NeSyS), a framework that integrates the probabilistic semantic priors of LLMs with executable symbolic rules to achieve both expressivity and robustness. NeSyS alternates training between the two models using trajectories inadequately explained by the other. Unlike rule-based prompting, the symbolic WM directly constrains the LLM by modifying its output probability distribution. The neural WM is fine-tuned only on trajectories not covered by symbolic rules, reducing training data by 50% without loss of accuracy. Extensive experiments on three distinct interactive environments, i.e., ScienceWorld, Webshop, and Plancraft, demonstrate NeSyS's consistent advantages over baselines in both WM prediction accuracy and data efficiency.